Spec4: Instructions file for Codex

AGENTS.md

Spec4 AGENTS.md is an instructions file for Codex, OpenCode from robertcrowe/Spec4. It costs 1,451 tokens per session, scanned A, original, no licence file.

A set of AGENTS.md instructions for the Spec4 project. It defines how the project treats completion gates, lint findings, type information, session keys, and state.

In plain words
What is it for?
It helps agents work on Spec4 while following its definition of done, lint decisions, typing, session, and state requirements.
Why use it?
It gives coding agents project-specific rules for deciding when work is complete and how to handle important implementation details.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is robertcrowe/Spec4's own configuration. It tells Codex and OpenCode how to work on Spec4 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Spec4 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to robertcrowe/Spec4. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/robertcrowe/Spec4/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/robertcrowe/Spec4

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Spec4 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robertcrowe/spec4/agents-md/github.svg)](https://agentmods.dev/instructions/robertcrowe/spec4/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/robertcrowe/spec4/agents-md"><img src="https://agentmods.dev/badge/instructions/robertcrowe/spec4/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Spec4 AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/robertcrowe/spec4/agents-md"><img src="https://agentmods.dev/badge/instructions/robertcrowe/spec4/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,451 This file is loaded in full into every session.
When invoked 1,451 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01451 $0.01451
Opus 5.5 $0.00580 $0.00580
Sonnet 5.5 $0.00290 $0.00290
Haiku 4.5 $0.00145 $0.00145

Measured 1mo ago against content hash 14193886caaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Spec4 AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 114 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 114 lines · 1,451 tokens per session scan A 14193886caaf

Subscribe to this mod's changes

Spec4 AGENTS.md is an instructions file published in the GitHub repository robertcrowe/Spec4 (13 stars, last pushed 11d ago), with no licence file. It adds 1,451 tokens to every session, about $0.0058 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.

Related

Spec4 AGENTS.md compared with instructions from other repositories

Spec4 AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Spec4 AGENTS.mdrobertcrowe/Spec4Instructions file1311d agononeA1,451Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode